The document provides instructions for completing a practical assignment on analyzing a dataset about domestic tourism in South Africa. It describes three case studies to complete: 1) creating a cross-tabulation to investigate relationships between variables, 2) creating a scatter plot with a trendline to examine the covariance and correlation between two variables, and 3) creating a histogram to visualize the distribution of values for one variable. The document provides guidance on the required functions, formatting of outputs, and what will be expected on the online submission platform.
The document provides instructions for completing a practical assignment on analyzing a dataset about domestic tourism in South Africa. It describes three case studies to complete: 1) creating a cross-tabulation to investigate relationships between variables, 2) creating a scatter plot with a trendline to examine the covariance and correlation between two variables, and 3) creating a histogram to visualize the distribution of values for one variable. The document provides guidance on the required functions, formatting of outputs, and what will be expected on the online submission platform.
The document provides instructions for completing a practical assignment on analyzing a dataset about domestic tourism in South Africa. It describes three case studies to complete: 1) creating a cross-tabulation to investigate relationships between variables, 2) creating a scatter plot with a trendline to examine the covariance and correlation between two variables, and 3) creating a histogram to visualize the distribution of values for one variable. The document provides guidance on the required functions, formatting of outputs, and what will be expected on the online submission platform.
The document provides instructions for completing a practical assignment on analyzing a dataset about domestic tourism in South Africa. It describes three case studies to complete: 1) creating a cross-tabulation to investigate relationships between variables, 2) creating a scatter plot with a trendline to examine the covariance and correlation between two variables, and 3) creating a histogram to visualize the distribution of values for one variable. The document provides guidance on the required functions, formatting of outputs, and what will be expected on the online submission platform.
In order to complete an attempt in the allocated time, you will need to prepare properly before opening an attempt. Work through each of the case studies and make sure that you have mastered the techniques involved. You should also understand your results and be able to interpret them. You will be allowed a limited number of attempts for each practical, each with a fixed time limit. The best attempt will count. Each attempt will contain different questions. Each attempt needs to be done in one sitting, in other words, you cannot save and continue later. Should you exit the attempt before entering all your answers, you will be unable to complete the attempt and will have to start a new attempt. It is your responsibility to not submit an empty/incomplete attempt and no additional attempts will be provided. You need to complete your practical on a computer (desktop or laptop) NOT a phone or tablet. Use Google Chrome or Mozilla FireFox. DO NOT use Internet Explorer as your assignment may not open correctly in this browser.
Overview of the “Daytrips” dataset
For this practical you will be using sample data obtained by STATS SA in 2017 through the Domestic Tourism survey. The dataset (Daytrips.xlsx) contains information related to individuals who have taken day trips in the past three months, their households and living conditions, as well as information related to their most recent day trip. The original dataset (in coded format) can be downloaded from http://nesstar.statssa.gov.za:8282/webview/. However, the dataset has already been decoded with irrelevant variables and observations removed. The Daytrips.pdf document on MindTap/ClickUP contains descriptions of the variables found in the dataset. A few things to take note of: Only respondents who made at least one day trip in the three months prior to taking part in the survey are included in the dataset. A day trip is defined as a trip where the respondent travelled further than 40km from their home. Some of the respondents left some of the questions unanswered.
Objectives In this practical you will be expected to apply the theory learned in STK110 to a dataset in Excel in terms of graphical and tabular representations of data, and the interpretation of the above.
Functions and tools included in this practical
In this practical you may be expected to make use of the following functions/tools. PivotTable tool Chart tool Histogram tool CORREL COVARIANCE.S
1 STK110 Practical 1 202 4 Instructions • Submit your solutions on ClickUP before Friday, 08 March 2024, 16:00. No late submissions will be possible or accepted. • You will be allowed three attempts. Only the best attempt will count. • You will be allowed 60 minutes to complete an attempt.
Case Study 1: Crosstabulations
We would like to investigate the relationship between a respondent’s type of dwelling (column J) and whether or not they have access to a home/landline telephone (column U). This can be done by setting up a crosstabulation using Excel’s PivotTable tool. The result is shown below:
Hints: Click on any cell in the original dataset, then click on Insert -> PivotTable. The entire dataset should be selected automatically to be included in the PivotTable. You can then drag the required variables to the rows, columns and values boxes. This procedure is explained in Section 2.1 of your Practical Guide. The order of your columns and rows can be changed by right-clicking on the relevant column/row and selecting the appropriate “Move” option. Blank responses can be filtered out if required, leading to the output below:
What will be expected of you on ClickUP?
You will be provided with 2 variables to use in your crosstabulation. Use this to: complete the crosstabulation on ClickUP, and answer questions on ClickUP based on the results of your crosstabulation.
2 Case Study 2: Scatter plots and Trendlines Use the guidelines given in Section 2.5 of your Practical Guide to set up the scatter plot below.
We would like to investigate a possible relationship between the amount of money spent on land transport (column BQ) and on shopping (column BW) during a day trip. Place shopping on your horizontal axis and land transport on the vertical axis (see hints below).
Calculate the covariance and correlation between these two variables and check that your answers correspond to the values below. Covariance: 42972.88 Correlation: 0.11209
Hints: If you highlight land transport and shopping and insert a scatter plot, Excel will automatically place land transport on the horizontal axis and shopping on the vertical axis. This happens because the land transport column occurs first in the Excel sheet. To place land transport on the horizontal axis, copy both columns into a new sheet, but paste shopping in the first column and land transport in the second. When you now highlight these new columns and insert the scatter plot, shopping will be on the horizontal axis. When you insert your trendline, select the boxes to display the equation of the trendline as well as the 𝑅 value on the chart.
What will be expected of you on ClickUP?
You will be provided with 2 variables to use in your scatterplot. Use this to: create a scatterplot with appropriate and descriptive labels and titles, find the covariance and correlation between these variables, and fit a linear trendline to the scatterplot.
3 Case Study 3: Histograms Section 2.4 of your Practical Guide outlines the steps for setting up a histogram using the Histogram tool. A tutorial video for the histogram tool is provided on ClickUP.
We would like to investigate the amount of money spent in land transport (column BQ) during a day trip. Start the intervals for your histogram at 0 with the last interval having an upper limit of 600 and classes having a width of 50.
Steps: 1. Copy the entire column into a new sheet. To highlight the entire column, place the curser over the column label (BQ) and a black arrow pointing down will appear. Now click and then copy the data. Create a new worksheet, click in the first cell and paste the data here. 2. Create a column for the class limits (typically called bin values). 3. Select Data Analysis in the Data Ribbon and select the Histogram tool.
4. Select the data and class limits and indicate where the output needs to be placed. Also indicate that a chart should be created. In the screenshot below, note that The entire column A has been selected as input. It is much faster to select the entire column than to select the data itself (all empty cells will be ignored). Only the cells containing the “Bin” values should be selected, not the entire column. Selecting the entire column of “Bin” values may lead to your computer crashing. If the columns have titles, it is important to select the Labels box. An error will occur if this is not done.
4 The histogram obtained through this process is shown below:
A histogram should not have gaps between the different bars, so close these by right clicking on any of the bars, selecting Format Data Series... and setting the gap width to 0%.
Note that the histogram should have an appropriate, descriptive title and labels.
What will be expected of you on ClickUP?
You will be provided with a variable to use in your histogram. Use this to: create a histogram with appropriate and descriptive labels and titles, identify the distribution shape of the data based on the histogram, and answer questions on ClickUP based on your histogram.
